AAAI22 On Explainable AI Tools XAI Coding And Engineering Practices

YOUR LINK HERE:

http://youtube.com/watch?v=07hifxAsXjc

This video is about: Explainable AI - Tools - XAI Coding And Engineering Practices - tutorial presented at AAAI 2022 on February 22 (Virtual event - 600+ participants) • Who: Freddy Lecue, Fosca Giannotti, Riccardo Guidotti and Pasquale Minervini • Web site: https://xaitutorial2022.github.io/ • Slides: http://www-sop.inria.fr/members/Fredd... • Code: https://github.com/flecue/xai-aaai2022 • AAAI: https://aaai.org/Conferences/AAAI-22/... • Overview: • The future of AI lies in enabling people to collaborate with machines to solve complex problems. Like any efficient collaboration, this requires good communication, trust, clarity and understanding. XAI (eXplainable AI) aims at addressing such challenges by combining the best of symbolic AI and traditional Machine Learning. Such topic has been studied for years by all different communities of AI, with different definitions, evaluation metrics, motivations and results. • This tutorial is a snapshot on the work of XAI to date, and surveys the work achieved by the AI community with a focus on machine learning and symbolic AI related approaches (given the halfday format). We will motivate the needs of XAI in real-world and large-scale application, while presenting state-of-the-art techniques, with best XAI coding practices. In the first part of the tutorial, we give an introduction to the different aspects of explanations in AI. We then focus the tutorial on two specific approaches: (i) XAI using machine learning and (ii) XAI using a combination of graph-based knowledge representation and machine learning. For both we get into the specifics of the approach, the state of the art and the research challenges for the next steps. The final part of the tutorial gives an overview of real-world applications of XAI as well as best XAI coding practices. • Agenda • Part I: Introduction and Motivation - 20 minutes • Part II: Explanation in AI (not only Machine Learning!) - 40 minutes • Part III: On The Role of Knowledge Graphs in Explainable Machine Learning - 40 minutes • Part IV: XAI Tools, Coding and Engineering Practices - 40 minutes • Part V: XAI Applications, Lessons Learnt and Research Challenges - 40 minutes

#############################

New on site